更新CRF词法分析模型

hankcs · Jul 2, 2018 · 049f849 · 049f849
1 parent eae3b71
commit 049f849
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 5 deletions.
diff --git a/src/main/java/com/hankcs/hanlp/HanLP.java b/src/main/java/com/hankcs/hanlp/HanLP.java
@@ -172,15 +172,15 @@ public static final class Config
         /**
          * CRF分词模型
          */
-        public static String CRFCWSModelPath = "data/model/crf/pku199801/cws.bin";
+        public static String CRFCWSModelPath = "data/model/crf/pku199801/cws.txt";
         /**
          * CRF词性标注模型
          */
-        public static String CRFPOSModelPath = "data/model/crf/pku199801/pos.bin";
+        public static String CRFPOSModelPath = "data/model/crf/pku199801/pos.txt";
         /**
          * CRF命名实体识别模型
          */
-        public static String CRFNERModelPath = "data/model/crf/pku199801/ner.bin";
+        public static String CRFNERModelPath = "data/model/crf/pku199801/ner.txt";
         /**
          * 感知机分词模型
          */

diff --git a/src/main/java/com/hankcs/hanlp/model/crf/CRFNERecognizer.java b/src/main/java/com/hankcs/hanlp/model/crf/CRFNERecognizer.java
@@ -55,6 +55,7 @@ public CRFNERecognizer(String modelPath) throws IOException
         else
         {
             perceptronNERecognizer = new PerceptronNERecognizer(this.model);
+            tagSet = perceptronNERecognizer.getNERTagSet();
         }
     }
 

diff --git a/src/test/java/com/hankcs/demo/DemoMultithreadingSegment.java b/src/test/java/com/hankcs/demo/DemoMultithreadingSegment.java
@@ -11,9 +11,12 @@
 package com.hankcs.demo;
 
 import com.hankcs.hanlp.HanLP;
+import com.hankcs.hanlp.model.crf.CRFLexicalAnalyzer;
 import com.hankcs.hanlp.seg.CRF.CRFSegment;
 import com.hankcs.hanlp.seg.Segment;
 
+import java.io.IOException;
+
 /**
  * 演示多线程并行分词
  * 由于HanLP的任何分词器都是线程安全的，所以用户只需调用一个配置接口就可以启用任何分词器的并行化
@@ -22,9 +25,9 @@
  */
 public class DemoMultithreadingSegment
 {
-    public static void main(String[] args)
+    public static void main(String[] args) throws IOException
     {
-        Segment segment = new CRFSegment(); // CRF分词器效果好，速度慢，并行化之后可以提高一些速度
+        Segment segment = new CRFLexicalAnalyzer(HanLP.Config.CRFCWSModelPath).enableCustomDictionary(false); // CRF分词器效果好，速度慢，并行化之后可以提高一些速度
 
         String text = "举办纪念活动铭记二战历史，不忘战争带给人类的深重灾难，是为了防止悲剧重演，确保和平永驻；" +
                 "铭记二战历史，更是为了提醒国际社会，需要共同捍卫二战胜利成果和国际公平正义，" +